[MachinePipeliner] Fix constraints aren't considered in certain cases

when scheduling

When scheduling an instruction, if both any predecessors and any
successors of the instruction are already scheduled, `SchedStart` isn't
taken into account. It may result generating incorrect code. This patch
fixes the problem.

Author: kasuga-fj

llvm/include/llvm/CodeGen/MachinePipeliner.h

@@ -594,8 +594,8 @@ class SMSchedule {
   /// chain.
   int latestCycleInChain(const SDep &Dep);
 
-  void computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart,
-                    int *MinEnd, int *MaxStart, int II, SwingSchedulerDAG *DAG);
+  void computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart, int II,
+                    SwingSchedulerDAG *DAG);
   bool insert(SUnit *SU, int StartCycle, int EndCycle, int II);
 
   /// Iterators for the cycle to instruction map.
@@ -653,6 +653,9 @@ class SMSchedule {
   bool isLoopCarried(const SwingSchedulerDAG *SSD, MachineInstr &Phi) const;
   bool isLoopCarriedDefOfUse(const SwingSchedulerDAG *SSD, MachineInstr *Def,
                              MachineOperand &MO) const;
+
+  bool onlyHasLoopCarriedOutputOrOrderPreds(SUnit *SU,
+                                            SwingSchedulerDAG *DAG) const;
   void print(raw_ostream &os) const;
   void dump() const;
 };

llvm/lib/CodeGen/MachinePipeliner.cpp

@@ -2420,47 +2420,43 @@ bool SwingSchedulerDAG::schedulePipeline(SMSchedule &Schedule) {
       // upon the scheduled time for any predecessors/successors.
       int EarlyStart = INT_MIN;
       int LateStart = INT_MAX;
-      // These values are set when the size of the schedule window is limited
-      // due to chain dependences.
-      int SchedEnd = INT_MAX;
-      int SchedStart = INT_MIN;
-      Schedule.computeStart(SU, &EarlyStart, &LateStart, &SchedEnd, &SchedStart,
-                            II, this);
+      Schedule.computeStart(SU, &EarlyStart, &LateStart, II, this);
       LLVM_DEBUG({
         dbgs() << "\n";
         dbgs() << "Inst (" << SU->NodeNum << ") ";
         SU->getInstr()->dump();
         dbgs() << "\n";
       });
-      LLVM_DEBUG({
-        dbgs() << format("\tes: %8x ls: %8x me: %8x ms: %8x\n", EarlyStart,
-                         LateStart, SchedEnd, SchedStart);
-      });
+      LLVM_DEBUG(
+          dbgs() << format("\tes: %8x ls: %8x\n", EarlyStart, LateStart));
 
-      if (EarlyStart > LateStart || SchedEnd < EarlyStart ||
-          SchedStart > LateStart)
+      if (EarlyStart > LateStart)
         scheduleFound = false;
-      else if (EarlyStart != INT_MIN && LateStart == INT_MAX) {
-        SchedEnd = std::min(SchedEnd, EarlyStart + (int)II - 1);
-        scheduleFound = Schedule.insert(SU, EarlyStart, SchedEnd, II);
-      } else if (EarlyStart == INT_MIN && LateStart != INT_MAX) {
-        SchedStart = std::max(SchedStart, LateStart - (int)II + 1);
-        scheduleFound = Schedule.insert(SU, LateStart, SchedStart, II);
-      } else if (EarlyStart != INT_MIN && LateStart != INT_MAX) {
-        SchedEnd =
-            std::min(SchedEnd, std::min(LateStart, EarlyStart + (int)II - 1));
-        // When scheduling a Phi it is better to start at the late cycle and go
-        // backwards. The default order may insert the Phi too far away from
-        // its first dependence.
-        if (SU->getInstr()->isPHI())
-          scheduleFound = Schedule.insert(SU, SchedEnd, EarlyStart, II);
+      else if (EarlyStart != INT_MIN && LateStart == INT_MAX)
+        scheduleFound =
+            Schedule.insert(SU, EarlyStart, EarlyStart + (int)II - 1, II);
+      else if (EarlyStart == INT_MIN && LateStart != INT_MAX)
+        scheduleFound =
+            Schedule.insert(SU, LateStart, LateStart - (int)II + 1, II);
+      else if (EarlyStart != INT_MIN && LateStart != INT_MAX) {
+        LateStart = std::min(LateStart, EarlyStart + (int)II - 1);
+        // When scheduling a Phi it is better to start at the late cycle and
+        // go backwards. The default order may insert the Phi too far away
+        // from its first dependence.
+        // Also, do backward search when all scheduled predecessors are
+        // loop-carried output/order dependencies. Empirically, there are also
+        // cases where scheduling becomes possible with backward search.
+        if (SU->getInstr()->isPHI() ||
+            Schedule.onlyHasLoopCarriedOutputOrOrderPreds(SU, this))
+          scheduleFound = Schedule.insert(SU, LateStart, EarlyStart, II);
         else
-          scheduleFound = Schedule.insert(SU, EarlyStart, SchedEnd, II);
+          scheduleFound = Schedule.insert(SU, EarlyStart, LateStart, II);
       } else {
         int FirstCycle = Schedule.getFirstCycle();
         scheduleFound = Schedule.insert(SU, FirstCycle + getASAP(SU),
                                         FirstCycle + getASAP(SU) + II - 1, II);
       }
+
       // Even if we find a schedule, make sure the schedule doesn't exceed the
       // allowable number of stages. We keep trying if this happens.
       if (scheduleFound)
@@ -2868,8 +2864,7 @@ static SUnit *multipleIterations(SUnit *SU, SwingSchedulerDAG *DAG) {
 /// Compute the scheduling start slot for the instruction.  The start slot
 /// depends on any predecessor or successor nodes scheduled already.
 void SMSchedule::computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart,
-                              int *MinEnd, int *MaxStart, int II,
-                              SwingSchedulerDAG *DAG) {
+                              int II, SwingSchedulerDAG *DAG) {
   // Iterate over each instruction that has been scheduled already.  The start
   // slot computation depends on whether the previously scheduled instruction
   // is a predecessor or successor of the specified instruction.
@@ -2888,7 +2883,7 @@ void SMSchedule::computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart,
             *MaxEarlyStart = std::max(*MaxEarlyStart, EarlyStart);
             if (DAG->isLoopCarriedDep(SU, Dep, false)) {
               int End = earliestCycleInChain(Dep) + (II - 1);
-              *MinEnd = std::min(*MinEnd, End);
+              *MinLateStart = std::min(*MinLateStart, End);
             }
           } else {
             int LateStart = cycle - Dep.getLatency() +
@@ -2912,7 +2907,7 @@ void SMSchedule::computeStart(SUnit *SU, int *MaxEarlyStart, int *MinLateStart,
             *MinLateStart = std::min(*MinLateStart, LateStart);
             if (DAG->isLoopCarriedDep(SU, Dep)) {
               int Start = latestCycleInChain(Dep) + 1 - II;
-              *MaxStart = std::max(*MaxStart, Start);
+              *MaxEarlyStart = std::max(*MaxEarlyStart, Start);
             }
           } else {
             int EarlyStart = cycle + Dep.getLatency() -
@@ -3105,6 +3100,19 @@ bool SMSchedule::isLoopCarriedDefOfUse(const SwingSchedulerDAG *SSD,
   return false;
 }
 
+/// Return true if all scheduled predecessors are loop-carried output/order
+/// dependencies.
+bool SMSchedule::onlyHasLoopCarriedOutputOrOrderPreds(
+    SUnit *SU, SwingSchedulerDAG *DAG) const {
+  for (const SDep &Pred : SU->Preds)
+    if (InstrToCycle.count(Pred.getSUnit()) && !DAG->isBackedge(SU, Pred))
+      return false;
+  for (const SDep &Succ : SU->Succs)
+    if (InstrToCycle.count(Succ.getSUnit()) && DAG->isBackedge(SU, Succ))
+      return false;
+  return true;
+}
+
 /// Determine transitive dependences of unpipelineable instructions
 SmallSet<SUnit *, 8> SMSchedule::computeUnpipelineableNodes(
     SwingSchedulerDAG *SSD, TargetInstrInfo::PipelinerLoopInfo *PLI) {